© 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. 11-RESID-POST-AA
    11. 110654
    Prev
    Next
    INDEX
    Explanations

    <|end|>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Remote
    -0.09
    랙
    -0.09
    (sock
    -0.08
    (remote
    -0.08
    δευ
    -0.08
     Sunderland
    -0.08
     modem
    -0.08
     votação
    -0.08
     Athens
    -0.08
     picturesque
    -0.08
    POSITIVE LOGITS
    #region
    0.09
     ensure
    0.07
    ants
    0.07
    _SCOPE
    0.07
    ================================================================================
    0.07
    any
    0.07
    pink
    0.07
     Ensure
    0.07
    INTRO
    0.07
    宣传
    0.07
    Activations Density 0.009%

    No Known Activations