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. 15-RESID-POST-AA
    6. 19463
    Prev
    Next
    INDEX
    Explanations

    Money and resources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LICK
    -0.08
     state's
    -0.08
    atuan
    -0.07
    Track
    -0.07
    oid
    -0.07
    ịnh
    -0.07
    -0.07
    Abort
    -0.07
    osis
    -0.07
     etiquette
    -0.07
    POSITIVE LOGITS
     realloc
    0.14
     savings
    0.14
     freed
    0.13
     Savings
    0.13
     surplus
    0.12
     سایر
    0.12
     funds
    0.12
     allocate
    0.11
     redirected
    0.11
     gained
    0.11
    Activations Density 0.034%

    No Known Activations