© 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. 78943
    Prev
    Next
    INDEX
    Explanations

    Arrangement problems

    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
    .detect
    -0.08
    (write
    -0.08
     entregar
    -0.08
    resco
    -0.07
    (boolean
    -0.07
     అంట
    -0.07
    (page
    -0.07
    (V
    -0.07
    	rt
    -0.07
     кон
    -0.07
    POSITIVE LOGITS
     interven
    0.17
    _between
    0.13
     intervene
    0.13
     intermediary
    0.13
    -between
    0.12
     tussen
    0.12
    Intermediate
    0.12
     intermediate
    0.12
    Between
    0.12
     Intermediate
    0.11
    Activations Density 0.017%

    No Known Activations