© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44871
    Prev
    Next
    INDEX
    Explanations

    al

    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
     propiedad
    -0.08
     Stimme
    -0.07
    规律
    -0.07
     GLfloat
    -0.07
    fred
    -0.07
    缓存
    -0.07
     Hmm
    -0.07
     FIXME
    -0.07
     Bouquet
    -0.07
     olvidar
    -0.07
    POSITIVE LOGITS
    Executive
    0.08
     enclave
    0.08
     வீர
    0.08
     suicide
    0.08
     minuter
    0.08
    weets
    0.08
     authentic
    0.08
     kaya
    0.08
    weet
    0.08
     Finn
    0.07
    Activations Density 0.004%

    No Known Activations