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. 11-RESID-POST-AA
    6. 30438
    Prev
    Next
    INDEX
    Explanations

    resources

    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
     dispersed
    -0.09
     ঢাকা
    -0.08
     curt
    -0.08
     presumed
    -0.08
     pennies
    -0.08
    Pink
    -0.07
     periodic
    -0.07
    ২৩
    -0.07
    Pizza
    -0.07
     pizza
    -0.07
    POSITIVE LOGITS
     USER
    0.08
    êr
    0.08
    ioxid
    0.08
    -benef
    0.08
     antioxidant
    0.08
    fé
    0.08
    <?,
    0.08
    ADX
    0.08
     probi
    0.08
     bold
    0.07
    Activations Density 0.002%

    No Known Activations