© 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. 99154
    Prev
    Next
    INDEX
    Explanations

    genomics

    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
     izvaj
    -0.09
    GAIN
    -0.08
     المقبل
    -0.08
     convivial
    -0.08
     व्याप
    -0.08
     Treffen
    -0.08
    ’entrée
    -0.08
    Prefixes
    -0.07
     Foot
    -0.07
     worrying
    -0.07
    POSITIVE LOGITS
    _fixture
    0.09
     기준
    0.08
     refined
    0.08
    punkt
    0.08
     chromosome
    0.08
     string
    0.07
     refine
    0.07
     pn
    0.07
     movie
    0.07
     nanop
    0.07
    Activations Density 0.001%

    No Known Activations