© 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. 193
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    alty
    -0.09
     lento
    -0.08
     Moscow
    -0.08
    ige
    -0.08
    bh
    -0.07
     উ
    -0.07
     অবশ্য
    -0.07
     Khan
    -0.07
     Robert
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     quería
    0.10
     wenige
    0.10
     pochi
    0.10
     einzigen
    0.10
     wenigen
    0.09
     лишь
    0.09
     einzige
    0.09
    ，却
    0.09
     محدود
    0.09
    মাত্র
    0.09
    Activations Density 0.087%

    No Known Activations