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. 77300
    Prev
    Next
    INDEX
    Explanations

    mel

    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
     Philip
    -0.07
     Trent
    -0.07
     Urs
    -0.07
     not
    -0.07
     като
    -0.07
     Schw
    -0.07
     preventiva
    -0.07
    endera
    -0.07
    ascus
    -0.07
     trae
    -0.07
    POSITIVE LOGITS
     zoom
    0.09
    .zoom
    0.09
    zoom
    0.08
     �
    0.08
    (cr
    0.08
     Zoom
    0.08
    Zoom
    0.08
    _zoom
    0.07
     masters
    0.07
    Interpolation
    0.07
    Activations Density 0.000%

    No Known Activations