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. 77556
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
     inevitably
    -0.09
     inevitable
    -0.08
    Ub
    -0.08
     Fab
    -0.08
     trải
    -0.08
     gevo
    -0.07
    laser
    -0.07
     Eben
    -0.07
     illuminating
    -0.07
     mua
    -0.07
    POSITIVE LOGITS
     literal
    0.08
     literally
    0.08
     മൊ
    0.08
     shelf
    0.08
     চ
    0.07
     metaphor
    0.07
     seques
    0.07
     leck
    0.07
     intake
    0.07
     کھ
    0.07
    Activations Density 0.085%

    No Known Activations