© 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. 64916
    Prev
    Next
    INDEX
    Explanations

    -

    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
    ത്
    -0.09
     responds
    -0.08
    Respond
    -0.08
    Passing
    -0.07
    .rooms
    -0.07
     jawab
    -0.07
    ರ್ಜ
    -0.07
     Respond
    -0.07
     ambiguous
    -0.07
     réponse
    -0.07
    POSITIVE LOGITS
    )^
    0.09
     denial
    0.09
     vertra
    0.08
     Maf
    0.08
    ]^
    0.08
    тыру
    0.08
     owl
    0.07
    $wp
    0.07
     <$>
    0.07
    ubi
    0.07
    Activations Density 0.046%

    No Known Activations