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. 55868
    Prev
    Next
    INDEX
    Explanations

    mythical creatures

    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
    拟
    -0.10
     విక
    -0.07
    vuldig
    -0.07
    geme
    -0.07
     popup
    -0.07
    าส
    -0.07
     toon
    -0.07
    ঙ্গে
    -0.07
    .constraint
    -0.07
     konnte
    -0.07
    POSITIVE LOGITS
     chewing
    0.09
     billi
    0.09
    _cod
    0.09
     자세
    0.08
     cough
    0.08
     che
    0.08
    CHE
    0.08
    conce
    0.08
    éros
    0.08
     waitress
    0.08
    Activations Density 0.002%

    No Known Activations