© 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. 24605
    Prev
    Next
    INDEX
    Explanations

    information

    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
     pot
    -0.07
    tf
    -0.07
    _rgb
    -0.07
     hook
    -0.07
    র্ত
    -0.07
    ibre
    -0.07
     pud
    -0.07
    939
    -0.07
     dryers
    -0.07
     clutch
    -0.07
    POSITIVE LOGITS
     provenant
    0.09
     фак
    0.09
     bēr
    0.08
     사실
    0.08
     Cen
    0.08
     يجوز
    0.08
     बच्चे
    0.08
     Barn
    0.08
    습니까
    0.08
     Naar
    0.08
    Activations Density 0.017%

    No Known Activations