© 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. 7-RESID-POST-AA
    11. 1353
    Prev
    Next
    INDEX
    Explanations

    short time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ，然后
    -0.08
    万
    -0.07
     instantiated
    -0.07
    <
    -0.07
    ，并
    -0.07
    útbol
    -0.07
    -level
    -0.07
     comparing
    -0.07
    ples
    -0.06
    ಿಸಿದ
    -0.06
    POSITIVE LOGITS
     allotted
    0.10
     precious
    0.10
     સમયમાં
    0.10
    時間
    0.10
    期限
    0.09
     قصيرة
    0.09
     확보
    0.09
     limité
    0.09
     زمن
    0.09
    Urg
    0.09
    Activations Density 0.039%

    No Known Activations