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. 53144
    Prev
    Next
    INDEX
    Explanations

    university

    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
     उपाय
    -0.09
    _AX
    -0.08
    Driving
    -0.08
    tail
    -0.08
    tails
    -0.08
     неж
    -0.08
     Bride
    -0.07
     driving
    -0.07
    :].
    -0.07
     empowerment
    -0.07
    POSITIVE LOGITS
     Montpellier
    0.09
     faculty
    0.09
     профессор
    0.09
     교수
    0.08
     professor
    0.08
    论文
    0.08
    执
    0.08
     кафед
    0.08
     organs
    0.08
    教授
    0.08
    Activations Density 0.028%

    No Known Activations