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. 53074
    Prev
    Next
    INDEX
    Explanations

    tetra

    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
     JSP
    -0.09
     Swe
    -0.08
     ضبط
    -0.08
     Tela
    -0.08
     maslahat
    -0.08
     wash
    -0.08
     ~/.
    -0.07
    223
    -0.07
     tela
    -0.07
     rewind
    -0.07
    POSITIVE LOGITS
    Geometry
    0.09
    hedron
    0.09
    angi
    0.08
    Normals
    0.08
    ographed
    0.08
    _geometry
    0.08
    uca
    0.08
    _count
    0.08
    uum
    0.08
    isphere
    0.08
    Activations Density 0.005%

    No Known Activations