© 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. 95066
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning

    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
     unethical
    -0.09
     expos
    -0.08
    soa
    -0.08
     Nasdaq
    -0.08
     intensa
    -0.08
     incó
    -0.08
    膜
    -0.08
    _MUT
    -0.08
     ods
    -0.08
    Nicole
    -0.08
    POSITIVE LOGITS
     disponibilidad
    0.12
    availability
    0.12
    Availability
    0.11
     disponibil
    0.11
     heuristic
    0.11
     Availability
    0.11
     availability
    0.11
     disponibilité
    0.10
     disponibilidade
    0.10
    heur
    0.10
    Activations Density 0.031%

    No Known Activations