© 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. 107
    Prev
    Next
    INDEX
    Explanations

    1

    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
     boundary
    -0.08
     curiosity
    -0.07
     stupid
    -0.07
     containment
    -0.07
    в
    -0.07
     
    -0.07
     самой
    -0.07
    'instant
    -0.07
     teas
    -0.07
     config
    -0.07
    POSITIVE LOGITS
    onomy
    0.11
    larni
    0.10
    utut
    0.09
    see
    0.08
    laring
    0.08
    kaart
    0.08
    laag
    0.08
    .patch
    0.08
    ，其中
    0.08
    See
    0.08
    Activations Density 0.001%

    No Known Activations