© 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. 7-RESID-POST-AA
    11. 1251
    Prev
    Next
    INDEX
    Explanations

    init.py

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Limiter
    -0.08
     Ап
    -0.08
     spare
    -0.07
     verdad
    -0.07
     CURLOPT
    -0.07
     prescribed
    -0.07
    ั้น
    -0.07
     estima
    -0.07
     wirst
    -0.07
     prescription
    -0.07
    POSITIVE LOGITS
     chaleureux
    0.09
     gemeins
    0.08
    ("");
↵
    0.08
    Bienvenue
    0.08
     chaleure
    0.08
    ualitas
    0.08
     fəali
    0.08
    年代
    0.07
    Cargo
    0.07
     vorgestellt
    0.07
    Activations Density 0.002%

    No Known Activations