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. 53927
    Prev
    Next
    INDEX
    Explanations

    get

    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
    -0.08
     rpc
    -0.08
     toxicity
    -0.07
     lineup
    -0.07
    rpc
    -0.07
    odox
    -0.07
    baby
    -0.07
    ක්
    -0.07
     porc
    -0.07
     environments
    -0.07
    POSITIVE LOGITS
     nast
    0.09
     Initializes
    0.09
     있는
    0.08
     있으며
    0.08
     pren
    0.08
    nonatomic
    0.08
     atribu
    0.08
     élég
    0.07
     আছে
    0.07
    nullable
    0.07
    Activations Density 0.002%

    No Known Activations