Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 120439
    Prev
    Next
    INDEX
    Explanations

    Semicolons

    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
     costing
    -0.08
     سوق
    -0.08
    _Str
    -0.08
     გაი
    -0.08
     എണ്ണം
    -0.08
     გას
    -0.08
     Domingo
    -0.08
    秘
    -0.08
     എണ്ണ
    -0.07
     ਨਹ
    -0.07
    POSITIVE LOGITS
     stip
    0.09
    statement
    0.08
    kol
    0.08
     clauses
    0.08
    _statement
    0.07
    Signed
    0.07
    ∀
    0.07
     premise
    0.07
    utdown
    0.07
     Uri
    0.07
    Activations Density 0.028%

    No Known Activations