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. 56130
    Prev
    Next
    INDEX
    Explanations

    quantum computing

    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
     organisms
    -0.09
    fyr
    -0.08
     мов
    -0.08
     competing
    -0.08
     конкур
    -0.08
     jur
    -0.08
    نافس
    -0.08
     boutique
    -0.07
     fleeing
    -0.07
    .entities
    -0.07
    POSITIVE LOGITS
    Trigger
    0.09
    Cooldown
    0.08
    Overflow
    0.08
    Highlight
    0.08
    Separator
    0.08
    HEEL
    0.08
    Inst
    0.08
    Neighbour
    0.08
    Pickup
    0.07
    Exchange
    0.07
    Activations Density 0.001%

    No Known Activations