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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16470
    Prev
    Next
    INDEX
    Explanations

    Let/denote

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genuinely
    -0.10
    otechn
    -0.10
    (XML
    -0.09
    vimento
    -0.09
    psych
    -0.09
    (with
    -0.08
    Descripción
    -0.08
     באמת
    -0.08
    <|reserved_200004|>
    -0.08
    ...</
    -0.08
    POSITIVE LOGITS
     tmp
    0.12
     denote
    0.11
     equation
    0.11
     temp
    0.10
     Tmp
    0.09
     coef
    0.09
     denom
    0.09
     Eq
    0.09
     Equation
    0.08
    tmp
    0.08
    Activations Density 0.039%

    No Known Activations