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. 98510
    Prev
    Next
    INDEX
    Explanations

    content

    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
     توزيع
    -0.08
     admir
    -0.07
     HAS
    -0.07
    chal
    -0.07
    fav
    -0.07
    ipas
    -0.07
     cori
    -0.07
     garanti
    -0.07
     pronounce
    -0.07
     lubrication
    -0.07
    POSITIVE LOGITS
    .message
    0.10
    	message
    0.10
    /t
    0.09
    +t
    0.09
    .trim
    0.08
    .pad
    0.08
     повідом
    0.08
    mensaje
    0.08
    _t
    0.08
    utf
    0.08
    Activations Density 0.004%

    No Known Activations