© 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. 68260
    Prev
    Next
    INDEX
    Explanations

    code letters F and C

    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
     Gareth
    -0.10
     strenuous
    -0.09
     노동
    -0.09
     सामान
    -0.09
     ہاتھ
    -0.09
     Carp
    -0.09
     mante
    -0.08
     здоров
    -0.08
     carp
    -0.08
     vigor
    -0.08
    POSITIVE LOGITS
    530
    0.08
    161
    0.08
    Radio
    0.08
     phosph
    0.08
     radios
    0.08
    radio
    0.08
    020
    0.08
     radio
    0.08
    259
    0.08
    160
    0.07
    Activations Density 0.002%

    No Known Activations