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. 65227
    Prev
    Next
    INDEX
    Explanations

    Stretching money/budget

    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
     prerequisite
    -0.08
    本人
    -0.07
    好了
    -0.07
    ког
    -0.07
     confessed
    -0.07
    、お
    -0.07
    Flo
    -0.07
     prerequisites
    -0.07
    >{@
    -0.07
     large
    -0.07
    POSITIVE LOGITS
     dollars
    0.11
     Dollars
    0.11
    qtis
    0.09
     Pounds
    0.09
     Bulld
    0.09
     dollar
    0.09
     डॉलर
    0.09
     Forestry
    0.09
    -Dollar
    0.08
    _TRANSL
    0.08
    Activations Density 0.020%

    No Known Activations