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. 112451
    Prev
    Next
    INDEX
    Explanations

    Giving advice

    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
     eventual
    -0.08
     verkar
    -0.07
    ingly
    -0.07
    údio
    -0.07
    ing
    -0.07
     eventually
    -0.07
    _ind
    -0.07
    uro
    -0.07
    dep
    -0.07
    obj
    -0.07
    POSITIVE LOGITS
     Gelegenheit
    0.09
     נס
    0.08
     factories
    0.08
    -Friday
    0.08
     افزایش
    0.08
     דא
    0.08
    piar
    0.08
    ไซ
    0.08
     амал
    0.08
    בס
    0.08
    Activations Density 0.079%

    No Known Activations