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. 111822
    Prev
    Next
    INDEX
    Explanations

    Decluttering and file paths

    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
    ikl
    -0.08
     penetrate
    -0.08
     lessen
    -0.08
    강
    -0.08
     강화
    -0.08
    Pen
    -0.08
    降低
    -0.08
     עליה
    -0.07
     اک
    -0.07
     perfume
    -0.07
    POSITIVE LOGITS
     Worth
    0.09
    ాట
    0.09
     snapshots
    0.09
    	raw
    0.08
    Worth
    0.08
    арту
    0.08
     budou
    0.08
    ૂડ
    0.08
     Tur
    0.07
     utilizes
    0.07
    Activations Density 0.000%

    No Known Activations