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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 43767
    Prev
    Next
    INDEX
    Explanations

    pi

    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
     groter
    -0.08
     grote
    -0.08
     plante
    -0.08
     Alber
    -0.08
     بڑے
    -0.07
     grandes
    -0.07
    grote
    -0.07
     നടക്ക
    -0.07
    决
    -0.07
     ಎದು
    -0.07
    POSITIVE LOGITS
    adians
    0.09
     rotations
    0.09
    ్ఞ
    0.09
     కార్యక
    0.09
     restarting
    0.09
     tins
    0.08
     Pisces
    0.08
    Goto
    0.08
    _HOME
    0.08
     joyful
    0.08
    Activations Density 0.021%

    No Known Activations