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. 104057
    Prev
    Next
    INDEX
    Explanations

    psychology and therapy

    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
     ಪಡೆಯ
    -0.08
    ’ik
    -0.08
    ிக
    -0.08
     до
    -0.08
     raya
    -0.07
     ожид
    -0.07
    /se
    -0.07
     ಪಡೆ
    -0.07
    ინც
    -0.07
     rai
    -0.07
    POSITIVE LOGITS
    üne
    0.09
     elderly
    0.08
    phes
    0.08
     Muse
    0.08
    疯
    0.08
     Mandy
    0.07
     muze
    0.07
     Δεν
    0.07
    useum
    0.07
    .broadcast
    0.07
    Activations Density 0.000%

    No Known Activations