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. 44076
    Prev
    Next
    INDEX
    Explanations

    plank exercise variations

    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
    _DAT
    -0.08
     Hors
    -0.08
    _LENGTH
    -0.08
    _J
    -0.07
     жат
    -0.07
     Jo
    -0.07
     Capricorn
    -0.07
    _START
    -0.07
    JM
    -0.07
    _CONNECT
    -0.07
    POSITIVE LOGITS
     rotating
    0.09
    (toggle
    0.08
     hubo
    0.08
    ');?>↵
    0.08
    ',...↵
    0.08
    maphore
    0.08
     repeatedly
    0.08
     constantemente
    0.08
     કામ
    0.08
     alternating
    0.07
    Activations Density 0.001%

    No Known Activations