© 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. 6068
    Prev
    Next
    INDEX
    Explanations

    مش

    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
     snaps
    -0.08
    "$
    -0.08
    át
    -0.08
    
    -0.08
    -active
    -0.08
    ayet
    -0.07
    æ
    -0.07
     edição
    -0.07
    ග
    -0.07
    strings
    -0.07
    POSITIVE LOGITS
    روط
    0.12
    بوط
    0.10
    ترك
    0.10
    هود
    0.10
    بوك
    0.10
    كور
    0.09
    لول
    0.09
     شرط
    0.09
    تاح
    0.09
    مول
    0.09
    Activations Density 0.002%

    No Known Activations