© 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. 102272
    Prev
    Next
    INDEX
    Explanations

    titles/names

    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
     ALSO
    -0.08
    /per
    -0.07
     gotten
    -0.07
     Acne
    -0.07
    CESS
    -0.07
     definitivamente
    -0.07
     KR
    -0.07
     Hälfte
    -0.07
    -SE
    -0.07
    -contact
    -0.07
    POSITIVE LOGITS
    árez
    0.11
    <|endoftext|>
    0.09
    历山大发
    0.09
    ovich
    0.09
    ෙ
    0.09
    ambani
    0.08
    okovic
    0.08
    <|reserved_200016|>
    0.08
    artsen
    0.08
     Jr
    0.08
    Activations Density 0.144%

    No Known Activations