Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 130992
    Prev
    Next
    INDEX
    Explanations

    not

    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
    							 
    -0.08
     deceive
    -0.07
    mg
    -0.07
    TE
    -0.07
    Matt
    -0.07
    棒
    -0.07
     costing
    -0.07
    ikka
    -0.07
    Ha
    -0.07
     hauling
    -0.07
    POSITIVE LOGITS
     hospitalization
    0.08
    _TRIGGER
    0.08
     quint
    0.08
     صور
    0.08
    तील
    0.08
     ISR
    0.08
     المستخدمة
    0.07
     Δ
    0.07
     Gau
    0.07
    quito
    0.07
    Activations Density 0.007%

    No Known Activations