© 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. 11-RESID-POST-AA
    11. 95224
    Prev
    Next
    INDEX
    Explanations

    ://

    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
     mediated
    -0.08
     �
    -0.08
     faced
    -0.08
    positie
    -0.08
    /(?
    -0.08
    ువు
    -0.08
     madd
    -0.07
     bal
    -0.07
    Moderator
    -0.07
     tersedia
    -0.07
    POSITIVE LOGITS
     xmlns
    0.08
     فر
    0.08
    ния
    0.08
     الفر
    0.08
     Insider
    0.08
     בשנת
    0.08
     ('
    0.08
     Interior
    0.08
     ভিত
    0.07
     Outdoor
    0.07
    Activations Density 0.001%

    No Known Activations