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. 12185
    Prev
    Next
    INDEX
    Explanations

    eyeglasses

    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
     violent
    -0.09
     violently
    -0.09
     speeches
    -0.09
    Achievements
    -0.09
     powers
    -0.08
     achievements
    -0.08
    skraft
    -0.08
     ধর্ম
    -0.08
     strat
    -0.08
     power
    -0.08
    POSITIVE LOGITS
     обув
    0.09
     worn
    0.09
     VO
    0.09
     accessory
    0.09
     аксесс
    0.08
     glasses
    0.08
     handheld
    0.08
     circuitry
    0.08
     skinny
    0.08
    /fonts
    0.08
    Activations Density 0.007%

    No Known Activations