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. 12140
    Prev
    Next
    INDEX
    Explanations

    oxidation and corrosion resistance

    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
    -total
    -0.09
     total
    -0.08
    arle
    -0.08
    総
    -0.07
     оцен
    -0.07
     sentiment
    -0.07
     evaluating
    -0.07
     Rhe
    -0.07
    TOTAL
    -0.07
     sex
    -0.07
    POSITIVE LOGITS
    orme
    0.10
     السعودي
    0.08
    stdafx
    0.08
    /fire
    0.08
     constructive
    0.08
     préf
    0.08
     buhok
    0.08
     Pasadena
    0.07
     длин
    0.07
     السعودية
    0.07
    Activations Density 0.002%

    No Known Activations