© 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. 63175
    Prev
    Next
    INDEX
    Explanations

    af

    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
     Rome
    -0.08
    rique
    -0.08
     pressures
    -0.08
    stead
    -0.07
     elevate
    -0.07
    ende
    -0.07
     eikä
    -0.07
    armor
    -0.07
     vy
    -0.07
     romantic
    -0.07
    POSITIVE LOGITS
     Succ
    0.10
     succ
    0.09
    succ
    0.08
    ,'.
    0.08
    ейс
    0.08
    Succ
    0.08
    _Color
    0.08
     Chop
    0.07
     Erfol
    0.07
     [['
    0.07
    Activations Density 0.073%

    No Known Activations