© 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. 7-RESID-POST-AA
    11. 1434
    Prev
    Next
    INDEX
    Explanations

    Classical music

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poche
    -0.08
     conversation
    -0.08
     tet
    -0.08
     conscience
    -0.07
     ув
    -0.07
     constellation
    -0.07
    事业
    -0.07
     conversa
    -0.07
     tors
    -0.07
     algo
    -0.07
    POSITIVE LOGITS
    -tail
    0.08
     kies
    0.08
    .St
    0.08
    rä
    0.08
    ondon
    0.08
    rias
    0.07
    �
    0.07
    авяз
    0.07
    edde
    0.07
    _Header
    0.07
    Activations Density 0.004%

    No Known Activations