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. 55816
    Prev
    Next
    INDEX
    Explanations

    Animal size descriptions

    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
    SAFE
    -0.09
     SAFE
    -0.08
     محدود
    -0.08
    -safe
    -0.08
     güven
    -0.07
     safe
    -0.07
    safe
    -0.07
     legislators
    -0.07
     केवल
    -0.07
    'ed
    -0.07
    POSITIVE LOGITS
     majest
    0.09
     vermind
    0.08
     основания
    0.08
     majestic
    0.08
     rampant
    0.08
     AGR
    0.08
     épa
    0.08
     seamlessly
    0.08
     roar
    0.08
    .Appearance
    0.08
    Activations Density 0.009%

    No Known Activations