© 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. 29583
    Prev
    Next
    INDEX
    Explanations

    Spanish pseudocode algorithms

    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
    #index
    -0.08
    amiliar
    -0.08
    answered
    -0.08
     advocate
    -0.08
    满
    -0.08
     excerpts
    -0.08
     equiv
    -0.07
     answered
    -0.07
    akukan
    -0.07
    ."',
    -0.07
    POSITIVE LOGITS
     پایان
    0.12
     종료
    0.09
    结束
    0.09
     endet
    0.09
     ముగ
    0.08
    Declarations
    0.08
     סוף
    0.08
     ות
    0.08
     చివ
    0.08
     समाप्त
    0.08
    Activations Density 0.003%

    No Known Activations