Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112060
    Prev
    Next
    INDEX
    Explanations

    Javascript code

    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
    aliases
    -0.08
     aparência
    -0.08
    罪
    -0.08
     aliases
    -0.08
     hurt
    -0.07
    216
    -0.07
     james
    -0.07
     zvinhu
    -0.07
    эгд
    -0.07
     dead
    -0.07
    POSITIVE LOGITS
    RSS
    0.08
     perif
    0.07
     botón
    0.07
    _digit
    0.07
    (per
    0.07
     куп
    0.07
    _except
    0.07
     dí
    0.07
     펼
    0.07
     estre
    0.07
    Activations Density 0.000%

    No Known Activations