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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44708
    Prev
    Next
    INDEX
    Explanations

    cycle

    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
     Chow
    -0.09
     Michaels
    -0.08
     Vereins
    -0.08
    ocking
    -0.08
     Pisces
    -0.08
     glic
    -0.08
     ಮುಂದೆ
    -0.08
     reco
    -0.08
     Isl
    -0.08
     Daly
    -0.08
    POSITIVE LOGITS
     süre
    0.09
    zeiten
    0.08
    dauer
    0.08
    duration
    0.08
     lengths
    0.08
     оку
    0.08
    UA
    0.08
     동안
    0.07
     زمن
    0.07
     inzicht
    0.07
    Activations Density 0.015%

    No Known Activations