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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65041
    Prev
    Next
    INDEX
    Explanations

    AI generated texts

    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
     다
    -0.08
     dello
    -0.07
     нит
    -0.07
     accidental
    -0.07
    тифик
    -0.07
    centrum
    -0.07
    loid
    -0.07
     Pase
    -0.07
     हस्त
    -0.07
     Nim
    -0.07
    POSITIVE LOGITS
     свидетель
    0.07
     indicar
    0.07
    Ind
    0.07
    據
    0.07
    毫
    0.07
    Streams
    0.07
    <Integer
    0.07
    表示
    0.07
    您
    0.07
    Описание
    0.07
    Activations Density 0.038%

    No Known Activations