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. 59944
    Prev
    Next
    INDEX
    Explanations

    code differences

    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
    /&
    -0.09
    ?',
    -0.08
     GOLD
    -0.08
    CER
    -0.08
     Roi
    -0.08
    antie
    -0.08
     ]
    -0.07
     kestyon
    -0.07
    🙏
    -0.07
    Rol
    -0.07
    POSITIVE LOGITS
     assembled
    0.08
     lupa
    0.07
     erheb
    0.07
     console
    0.07
     wesentlich
    0.07
     tekn
    0.07
     salad
    0.07
     значительно
    0.07
     существенно
    0.07
     context
    0.07
    Activations Density 0.000%

    No Known Activations