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. 77116
    Prev
    Next
    INDEX
    Explanations

    German

    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
     trá
    -0.08
     Romeo
    -0.08
     için
    -0.08
     Tyler
    -0.08
    Parcel
    -0.08
    마다
    -0.08
    ogy
    -0.08
     Break
    -0.07
    mm
    -0.07
    Break
    -0.07
    POSITIVE LOGITS
     যেতে
    0.11
    ,并
    0.10
    됩니다
    0.10
    ,而
    0.10
    ಬಹುದು
    0.09
    できます
    0.09
     gegangen
    0.09
    되어
    0.09
     شوید
    0.09
    ,其中
    0.09
    Activations Density 0.079%

    No Known Activations