© 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. 51592
    Prev
    Next
    INDEX
    Explanations

    、

    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
     logs
    -0.09
     unchecked
    -0.09
     flog
    -0.08
    logs
    -0.08
     flags
    -0.08
    ట్టి
    -0.08
    urrencies
    -0.08
     flag
    -0.08
    -he
    -0.08
    unchecked
    -0.08
    POSITIVE LOGITS
     Integrated
    0.15
     SH
    0.15
    Integrated
    0.13
     Partial
    0.12
     permutation
    0.11
    SH
    0.11
     Lime
    0.11
    Permutation
    0.11
    Partial
    0.10
     ICE
    0.10
    Activations Density 0.003%

    No Known Activations