© 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. 68272
    Prev
    Next
    INDEX
    Explanations

    user input code

    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
    ৎ
    -0.08
     aberr
    -0.07
     studi
    -0.07
     signaling
    -0.07
    �
    -0.07
    encoded
    -0.07
    pred
    -0.07
     andet
    -0.07
     asserting
    -0.06
    Nep
    -0.06
    POSITIVE LOGITS
    .prompt
    0.16
    .ask
    0.14
    (prompt
    0.14
     prompted
    0.14
     안내
    0.13
     Questionnaire
    0.12
     questionnaire
    0.12
     diálogo
    0.12
    _dialog
    0.12
     questionnaires
    0.11
    Activations Density 0.021%

    No Known Activations