© 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. 99212
    Prev
    Next
    INDEX
    Explanations

    nut

    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
    တာ
    -0.08
     stellen
    -0.08
    าพ
    -0.08
     EObject
    -0.07
     memb
    -0.07
     вашему
    -0.07
     steer
    -0.07
     põ
    -0.07
    erge
    -0.07
     enact
    -0.07
    POSITIVE LOGITS
     declined
    0.08
    杂
    0.08
    .Card
    0.08
    /card
    0.08
     peanuts
    0.08
     Pumpkin
    0.08
    גיש
    0.07
    Lion
    0.07
     Lion
    0.07
    Perc
    0.07
    Activations Density 0.011%

    No Known Activations