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. 113869
    Prev
    Next
    INDEX
    Explanations

    website text snippets

    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
     ی
    -0.08
    TRANSFER
    -0.08
    ्काल
    -0.08
     numériques
    -0.07
    ीक
    -0.07
     uud
    -0.07
    -yourself
    -0.07
    ENDIF
    -0.07
     exceptionally
    -0.07
     œuvre
    -0.07
    POSITIVE LOGITS
     valamint
    0.08
    _file
    0.08
     ஆகிய
    0.08
     તથા
    0.07
    等等
    0.07
    以及
    0.07
     그리고
    0.07
     등의
    0.07
     beings
    0.07
     तथा
    0.07
    Activations Density 0.095%

    No Known Activations