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. 113800
    Prev
    Next
    INDEX
    Explanations

    +

    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
    ட்டி
    -0.08
    -grand
    -0.08
    back
    -0.07
     mercy
    -0.07
    ví
    -0.07
     확
    -0.07
    그
    -0.07
     Judy
    -0.07
     julọ
    -0.07
    LOL
    -0.07
    POSITIVE LOGITS
     produces
    0.09
     Ole
    0.08
     solvent
    0.08
     sunlight
    0.08
     Tablet
    0.08
     hend
    0.08
     ole
    0.08
     sql
    0.08
     Vegetable
    0.08
     Eltern
    0.08
    Activations Density 0.006%

    No Known Activations