Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 58615
    Prev
    Next
    INDEX
    Explanations

    hyperbola math

    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
     incentiv
    -0.09
     ಬು
    -0.08
     Zuma
    -0.08
     Navigator
    -0.08
     लगातार
    -0.08
    持续
    -0.08
     Highlights
    -0.08
     Bazaar
    -0.08
     forall
    -0.08
     treinta
    -0.08
    POSITIVE LOGITS
     axis
    0.12
    -axis
    0.12
     orientation
    0.11
    Orientation
    0.10
    Axis
    0.10
    _AXIS
    0.09
    .axis
    0.09
    _axis
    0.09
    axis
    0.09
     rotated
    0.09
    Activations Density 0.021%

    No Known Activations