© 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. 3-RESID-POST-AA
    11. 12759
    Prev
    Next
    INDEX
    Explanations

    pot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unseen
    -0.08
    $scope
    -0.07
     steam
    -0.07
    bel
    -0.07
    kt
    -0.07
     wajen
    -0.07
     GMC
    -0.07
    �
    -0.07
     prevista
    -0.07
    bian
    -0.07
    POSITIVE LOGITS
     quaternion
    0.08
     Haar
    0.08
     sintet
    0.08
     enthusiasm
    0.07
     meltdown
    0.07
     వ్యాఖ్య
    0.07
    _ACTIVE
    0.07
     diffuse
    0.07
    0.07
     soma
    0.07
    Activations Density 0.002%
    No Known Activations