© 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. 47173
    Prev
    Next
    INDEX
    Explanations

    emoticons

    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
     yaitu
    -0.08
     מתוך
    -0.08
     Trinity
    -0.08
     homer
    -0.08
     hog
    -0.08
    ointed
    -0.08
     และ
    -0.08
    ，又
    -0.08
     คือ
    -0.08
    病毒
    -0.08
    POSITIVE LOGITS
    SED
    0.09
     gated
    0.08
    _sched
    0.08
    _rad
    0.08
    requirements
    0.07
     Chung
    0.07
     Rit
    0.07
     واس
    0.07
     Cu
    0.07
    alsa
    0.07
    Activations Density 0.015%

    No Known Activations