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. 106134
    Prev
    Next
    INDEX
    Explanations

    dash

    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
     cadáver
    -0.08
     décrit
    -0.07
     demise
    -0.07
    音
    -0.07
     числа
    -0.07
     keç
    -0.07
     لـ
    -0.07
     Fig
    -0.07
     Brad
    -0.07
     ém
    -0.07
    POSITIVE LOGITS
    سون
    0.09
     اړ
    0.08
    �
    0.08
     mits
    0.08
    ibig
    0.08
    SSFCell
    0.08
    tọ
    0.08
    -Un
    0.08
    REN
    0.07
    basoke
    0.07
    Activations Density 0.000%

    No Known Activations