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. 43303
    Prev
    Next
    INDEX
    Explanations

    mathematical equations/functions

    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
    sess
    -0.08
     Celtic
    -0.08
     troop
    -0.08
     maes
    -0.08
     Van
    -0.07
     India
    -0.07
     Scarlet
    -0.07
    gas
    -0.07
    林
    -0.07
    enkil
    -0.07
    POSITIVE LOGITS
    .input
    0.08
    Returned
    0.08
    returns
    0.08
    .inputs
    0.08
     proced
    0.08
    -output
    0.08
    .from
    0.08
    .od
    0.07
    Output
    0.07
    odb
    0.07
    Activations Density 0.021%

    No Known Activations