© 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. 3-RESID-POST-AA
    11. 2757
    Prev
    Next
    INDEX
    Explanations

    Fun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emporal
    -0.08
    Sho
    -0.08
     organism
    -0.08
    ening
    -0.07
    pos
    -0.07
     Nit
    -0.07
    Nit
    -0.07
     Ky
    -0.07
     Pav
    -0.07
    ющих
    -0.07
    POSITIVE LOGITS
     Mell
    0.08
     перев
    0.08
    �
    0.08
     EI
    0.08
     بالن
    0.07
    链
    0.07
     offici
    0.07
     �
    0.07
     Höhen
    0.07
    �
    0.07
    Activations Density 0.006%

    No Known Activations