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. 49120
    Prev
    Next
    INDEX
    Explanations

    (

    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
     JAM
    -0.09
     Commentary
    -0.08
    Affordable
    -0.08
     देना
    -0.08
    าสิโน
    -0.07
     affordable
    -0.07
     fungerar
    -0.07
    وظ
    -0.07
     mmol
    -0.07
     HEL
    -0.07
    POSITIVE LOGITS
    -shaped
    0.13
     geometry
    0.11
    geometry
    0.10
    Geometry
    0.10
    状
    0.09
     Geometry
    0.09
    .Shape
    0.09
    _shape
    0.09
    .geom
    0.09
    _geometry
    0.09
    Activations Density 0.044%

    No Known Activations