© 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. 50782
    Prev
    Next
    INDEX
    Explanations

    Business terms

    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
    ingi
    -0.11
    ings
    -0.09
    ing
    -0.09
     kirk
    -0.08
    ਿੰਗ
    -0.08
    ible
    -0.08
    ingt
    -0.08
     Merry
    -0.08
    ingale
    -0.08
    'ing
    -0.08
    POSITIVE LOGITS
     acknowledgment
    0.09
     assessment
    0.09
     authentication
    0.09
     fulfillment
    0.08
     benefits
    0.08
     optimization
    0.08
     acknowledgement
    0.08
     attainment
    0.08
     réception
    0.08
     enhancement
    0.08
    Activations Density 0.671%

    No Known Activations