© 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. 6143
    Prev
    Next
    INDEX
    Explanations

    из

    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
     komplett
    -0.08
     multiplayer
    -0.08
     בתק
    -0.07
     اُس
    -0.07
     אַנ
    -0.07
    萌
    -0.07
    insurance
    -0.07
     mini
    -0.07
     Ked
    -0.07
     العودة
    -0.07
    POSITIVE LOGITS
    dracht
    0.08
    Holding
    0.08
    Mask
    0.08
    ati
    0.08
    位
    0.08
    Hold
    0.08
     Feast
    0.08
    Filter
    0.07
    Touch
    0.07
     sells
    0.07
    Activations Density 0.000%

    No Known Activations