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. 54069
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     acumul
    -0.09
     ارزش
    -0.09
    Tier
    -0.08
     em
    -0.08
     communist
    -0.08
     thunk
    -0.08
     tier
    -0.08
     remix
    -0.08
    ويات
    -0.08
     entertainment
    -0.08
    POSITIVE LOGITS
     coordinates
    0.11
     geometry
    0.11
     radius
    0.11
    _RADIUS
    0.11
     geometr
    0.11
    Ellipse
    0.11
     Coordinates
    0.11
    Coordinates
    0.10
     analyt
    0.10
    _radius
    0.10
    Activations Density 0.110%

    No Known Activations