© 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. 48063
    Prev
    Next
    INDEX
    Explanations

    SI

    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
     đưa
    -0.10
     inuus
    -0.09
    िन्छ
    -0.09
    ihat
    -0.09
    uprofen
    -0.09
     doigts
    -0.09
    וחד
    -0.09
    ückt
    -0.08
     dibdib
    -0.08
     bum
    -0.08
    POSITIVE LOGITS
    EM
    0.17
     EM
    0.12
    EMA
    0.11
    .EM
    0.11
    _EM
    0.10
     EMS
    0.09
     EMA
    0.09
    EMS
    0.09
     telemetry
    0.08
    SEM
    0.08
    Activations Density 0.001%

    No Known Activations