© 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. 65000
    Prev
    Next
    INDEX
    Explanations

    melting/fusion

    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
     tình
    -0.08
    יכם
    -0.08
     soaring
    -0.08
     bodily
    -0.08
    ğiniz
    -0.07
     Wahrheit
    -0.07
    یه
    -0.07
     خوش
    -0.07
    importe
    -0.07
     loudly
    -0.07
    POSITIVE LOGITS
    ICC
    0.09
    /C
    0.08
    orch
    0.08
     ACCEPT
    0.07
    cip
    0.07
     _
    0.07
     peer
    0.07
    <C
    0.07
     ઉ
    0.07
    /L
    0.07
    Activations Density 0.002%

    No Known Activations