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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 65225
    Prev
    Next
    INDEX
    Explanations

    segments being cut

    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
     sg
    -0.08
     Gregg
    -0.08
    -making
    -0.08
    sg
    -0.08
     sval
    -0.08
     presets
    -0.08
    -maker
    -0.08
     intrac
    -0.08
    575
    -0.07
     tier
    -0.07
    POSITIVE LOGITS
     Plane
    0.09
    Plane
    0.09
    Intersect
    0.08
     plane
    0.08
    _planes
    0.08
    ino
    0.08
    idzwa
    0.08
     Irr
    0.08
    Planes
    0.08
     produces
    0.08
    Activations Density 0.026%

    No Known Activations