© 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. 68110
    Prev
    Next
    INDEX
    Explanations

    Academic publication numbers

    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
    trans
    -0.08
    -0.07
    Rut
    -0.07
    jø
    -0.07
     Trans
    -0.07
    urgent
    -0.07
     खर
    -0.07
     Holl
    -0.07
    journ
    -0.07
     basa
    -0.07
    POSITIVE LOGITS
     Diamonds
    0.08
     civ
    0.07
     headache
    0.07
    едом
    0.07
     theaters
    0.07
     skies
    0.07
     Medina
    0.07
    ortes
    0.07
    ikul
    0.07
     maig
    0.07
    Activations Density 0.105%
    No Known Activations