© 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. 44814
    Prev
    Next
    INDEX
    Explanations

    Mechanical shafts and axles

    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
     lex
    -0.08
     énerg
    -0.08
    -ele
    -0.08
     jen
    -0.08
    itelist
    -0.07
    Lex
    -0.07
     ferv
    -0.07
     phr
    -0.07
     Lex
    -0.07
     aloe
    -0.07
    POSITIVE LOGITS
     shafts
    0.12
     shaft
    0.09
    (rotation
    0.09
     rotation
    0.09
    轴
    0.09
    rotation
    0.08
    _rotation
    0.08
    Rotation
    0.08
     governors
    0.08
     bumped
    0.08
    Activations Density 0.007%

    No Known Activations