Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60658
    Prev
    Next
    INDEX
    Explanations

    movement/direction

    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
    PY
    -0.08
     defect
    -0.08
     Ans
    -0.07
    Cont
    -0.07
     माना
    -0.07
     Walsh
    -0.07
    OO
    -0.07
    Common
    -0.07
     validated
    -0.07
    opi
    -0.07
    POSITIVE LOGITS
    并
    0.13
     जाकर
    0.13
     చేసి
    0.12
    並
    0.12
    ుకొని
    0.10
     ചെയ്ത്
    0.10
    ుకుని
    0.10
     होकर
    0.09
     чтобы
    0.09
    ,将
    0.09
    Activations Density 0.198%

    No Known Activations