© 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. 23-RESID-POST-AA
    11. 97362
    Prev
    Next
    INDEX
    Explanations

    Flavor profiles

    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
     formando
    -0.10
     forming
    -0.09
     depicting
    -0.09
     copying
    -0.09
    -copy
    -0.08
     изображения
    -0.08
     forme
    -0.08
    entuk
    -0.08
    २५
    -0.08
     FORM
    -0.08
    POSITIVE LOGITS
     touch
    0.22
     twist
    0.19
     touche
    0.18
     Touch
    0.17
    Touch
    0.16
    touch
    0.16
     edge
    0.16
     toque
    0.15
     feel
    0.15
     spin
    0.15
    Activations Density 0.050%

    No Known Activations