© 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. 19-RESID-POST-AA
    11. 102688
    Prev
    Next
    INDEX
    Explanations

    Non-English

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    standard
    -0.10
     standard
    -0.09
    }<
    -0.09
     distinctly
    -0.08
     responsabil
    -0.08
     estándar
    -0.07
    标准
    -0.07
    ехнолог
    -0.07
    distinct
    -0.07
    (subject
    -0.07
    POSITIVE LOGITS
    ariş
    0.09
    ieuwd
    0.09
     fã
    0.09
     famba
    0.08
    ază
    0.08
     submenu
    0.08
    andaag
    0.08
    itäten
    0.08
     TValue
    0.08
     τώρα
    0.08
    Activations Density 0.000%

    No Known Activations