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. 102934
    Prev
    Next
    INDEX
    Explanations

    1

    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
    derd
    -0.08
    mest
    -0.08
    vali
    -0.08
    aher
    -0.07
     дру
    -0.07
    Technology
    -0.07
    tol
    -0.07
     secrecy
    -0.07
    क्सी
    -0.07
    Distr
    -0.07
    POSITIVE LOGITS
     límite
    0.08
    为
    0.08
     للج
    0.07
     పొంద
    0.07
     sueño
    0.07
    获得
    0.07
    成人
    0.07
     esas
    0.07
    _max
    0.07
     provisional
    0.07
    Activations Density 0.033%

    No Known Activations