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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 76373
    Prev
    Next
    INDEX
    Explanations

    or

    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
     gezellige
    -0.08
     Specify
    -0.08
    leving
    -0.08
    编号
    -0.08
     kaum
    -0.08
     plutôt
    -0.08
     Kalk
    -0.08
    赛
    -0.08
     Número
    -0.08
    ელი
    -0.08
    POSITIVE LOGITS
     problematic
    0.10
     unnecessarily
    0.09
     frivol
    0.09
     undue
    0.09
     excessively
    0.09
    违规
    0.08
     prematurely
    0.08
     inappropriate
    0.08
    -
    0.08
     improperly
    0.08
    Activations Density 0.001%

    No Known Activations