© 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. 44912
    Prev
    Next
    INDEX
    Explanations

    Necessity

    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
     piet
    -0.09
    ége
    -0.08
    fruit
    -0.08
    iett
    -0.08
    ETH
    -0.07
    quotes
    -0.07
     eterno
    -0.07
    pau
    -0.07
    rous
    -0.07
    _)↵
    -0.07
    POSITIVE LOGITS
    \Validator
    0.08
     проще
    0.08
     खातिर
    0.08
     constrained
    0.08
     maxlength
    0.08
     алдында
    0.08
     превыш
    0.07
     дли
    0.07
     allowable
    0.07
    Restrictions
    0.07
    Activations Density 0.003%

    No Known Activations