© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51830
    Prev
    Next
    INDEX
    Explanations

    failures/errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     harmonious
    -0.08
     reliable
    -0.08
     illustrative
    -0.08
     enjoyable
    -0.07
     Bibli
    -0.07
     allowable
    -0.07
     affectionate
    -0.07
     accurate
    -0.07
     scalable
    -0.07
     customizable
    -0.07
    POSITIVE LOGITS
     mismatch
    0.27
     failures
    0.26
     failure
    0.25
     discrepancies
    0.25
     inaccuracies
    0.25
     violations
    0.25
     deficiencies
    0.24
     shortcomings
    0.24
     errors
    0.24
     imbalance
    0.24
    Activations Density 0.332%

    No Known Activations