© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 47964
    Prev
    Next
    INDEX
    Explanations

    ok

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Morgan
    -0.08
     Post
    -0.08
     Mar
    -0.08
    该
    -0.08
     Назар
    -0.07
     Dont
    -0.07
     Ciencia
    -0.07
    ко
    -0.07
     Not
    -0.07
     Zen
    -0.07
    POSITIVE LOGITS
     mascul
    0.10
    Enumer
    0.09
     enumerate
    0.08
     brainstorming
    0.08
    Visited
    0.08
     Enumer
    0.08
     प्रण
    0.08
    计划软件
    0.08
     кезд
    0.08
    osp
    0.08
    Activations Density 0.000%

    No Known Activations