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. 112061
    Prev
    Next
    INDEX
    Explanations

    refrigerant

    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
     majest
    -0.08
    ========
    -0.08
    ellers
    -0.08
    .HORIZONTAL
    -0.08
     tease
    -0.08
     stitched
    -0.07
     pourrez
    -0.07
     teasing
    -0.07
     entrances
    -0.07
    /month
    -0.07
    POSITIVE LOGITS
    Protocols
    0.09
     protocols
    0.08
    Protocol
    0.08
    -purpose
    0.08
    _used
    0.08
    raul
    0.07
    Used
    0.07
     procédures
    0.07
    trica
    0.07
     verwendet
    0.07
    Activations Density 0.005%

    No Known Activations