© 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. 19-RESID-POST-AA
    11. 103556
    Prev
    Next
    INDEX
    Explanations

    of

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dinge
    -0.08
    (global
    -0.08
    on
    -0.08
     asunto
    -0.08
    how
    -0.07
     global
    -0.07
    ansı
    -0.07
    upon
    -0.07
    asının
    -0.07
     cómo
    -0.07
    POSITIVE LOGITS
     them
    0.12
     них
    0.11
     Them
    0.10
    选四
    0.10
     niitä
    0.10
    Them
    0.09
    ･･･
    0.09
    <|reserved_200009|>
    0.09
     этих
    0.09
    <|return|>
    0.08
    Activations Density 0.016%

    No Known Activations