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. 106087
    Prev
    Next
    INDEX
    Explanations

    interview advice and tips

    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
     صفحات
    -0.09
     prohibit
    -0.08
     VBox
    -0.08
     avanzado
    -0.08
     календар
    -0.08
     Fél
    -0.08
    ADV
    -0.08
     dessen
    -0.07
     Pane
    -0.07
    اة
    -0.07
    POSITIVE LOGITS
     sincerity
    0.13
     articulate
    0.11
     articul
    0.10
     sincere
    0.10
     articulated
    0.10
     überzeug
    0.09
    回答
    0.09
    诚
    0.09
     प्रस्त
    0.09
     verbal
    0.09
    Activations Density 0.021%

    No Known Activations