© 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. 129495
    Prev
    Next
    INDEX
    Explanations

    symmetry

    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
    苗
    -0.09
     veggie
    -0.08
     фрукт
    -0.08
    Fruit
    -0.08
     vegetable
    -0.08
     drought
    -0.08
    Alerts
    -0.08
     fruit
    -0.08
    Subscription
    -0.08
    _sms
    -0.08
    POSITIVE LOGITS
     transpose
    0.16
    transpose
    0.15
    .transpose
    0.14
     Herm
    0.12
    Transpose
    0.12
     matrices
    0.11
     herm
    0.10
     centros
    0.10
     covariance
    0.10
    Herm
    0.10
    Activations Density 0.007%

    No Known Activations