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. 77115
    Prev
    Next
    INDEX
    Explanations

    Knowledge and social interactions

    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
    LABEL
    -0.08
    Princip
    -0.08
    였다
    -0.07
     resonates
    -0.07
    Niet
    -0.07
    पन
    -0.07
    났다
    -0.07
     nuclei
    -0.07
    utup
    -0.07
    (By
    -0.07
    POSITIVE LOGITS
     Rows
    0.08
    0.08
     Polish
    0.08
     Zd
    0.07
     fold
    0.07
     поль
    0.07
     bỏ
    0.07
     Odds
    0.07
     Fold
    0.07
    .Clone
    0.07
    Activations Density 0.000%

    No Known Activations