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. 46000
    Prev
    Next
    INDEX
    Explanations

    inline

    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
    ellus
    -0.08
    Login
    -0.07
    /how
    -0.07
    -do
    -0.07
    기의
    -0.07
    Tod
    -0.07
    cand
    -0.07
     ukwuu
    -0.07
    Envelope
    -0.07
    Nearby
    -0.07
    POSITIVE LOGITS
    0.09
     maupun
    0.09
     Sachs
    0.08
     Прод
    0.08
    опат
    0.08
     prejud
    0.08
     Matte
    0.08
     шах
    0.08
     Shannon
    0.08
    แข่งขัน
    0.08
    Activations Density 0.002%

    No Known Activations