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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 46980
    Prev
    Next
    INDEX
    Explanations

    Positive sentiment

    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
     נוספים
    -0.08
     twin
    -0.08
     weitere
    -0.08
     dry
    -0.08
    kia
    -0.08
     weiteren
    -0.07
     whirl
    -0.07
     lanc
    -0.07
     tov
    -0.07
    KIT
    -0.07
    POSITIVE LOGITS
     than
    0.26
    _than
    0.26
    -than
    0.24
    Than
    0.24
    _THAN
    0.23
    、更
    0.21
    than
    0.21
     niż
    0.21
     THAN
    0.19
     Than
    0.19
    Activations Density 0.539%

    No Known Activations