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. 44055
    Prev
    Next
    INDEX
    Explanations

    measurements

    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
    693
    -0.09
    231
    -0.09
     وتت
    -0.09
     అయ
    -0.08
     HRESULT
    -0.08
     Clicking
    -0.08
     Aby
    -0.08
     :-
    -0.08
     また
    -0.08
    .When
    -0.08
    POSITIVE LOGITS
     rod
    0.07
     high
    0.07
     crise
    0.07
     نظام
    0.07
     ઉચ્ચ
    0.07
    关于
    0.07
     ар
    0.07
    \t
    0.07
    Vel
    0.07
    س
    0.07
    Activations Density 0.054%

    No Known Activations