© 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. 6185
    Prev
    Next
    INDEX
    Explanations

    hypoc

    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
    atora
    -0.08
     Montage
    -0.08
    ector
    -0.08
    aren
    -0.08
    规划
    -0.08
    azwa
    -0.08
    _mex
    -0.08
    -bars
    -0.07
    .Vector
    -0.07
     Forma
    -0.07
    POSITIVE LOGITS
    rites
    0.12
    ritical
    0.12
    riting
    0.12
     hypocrisy
    0.12
    rite
    0.10
    hrases
    0.09
     hypocr
    0.09
    hrase
    0.09
     righteousness
    0.08
    riters
    0.08
    Activations Density 0.001%

    No Known Activations