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. 58932
    Prev
    Next
    INDEX
    Explanations

    ENGINE

    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
    sprecher
    -0.09
     соч
    -0.08
     चोट
    -0.08
     escort
    -0.08
     circuitry
    -0.08
     illusion
    -0.08
    _EXPR
    -0.08
    ocular
    -0.07
     нар
    -0.07
     ECG
    -0.07
    POSITIVE LOGITS
     ynd
    0.08
    (New
    0.08
     Preference
    0.08
    flags
    0.08
     vár
    0.08
    @Table
    0.08
     Service
    0.07
    Ω
    0.07
     físicas
    0.07
    Preference
    0.07
    Activations Density 0.001%

    No Known Activations