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. 112254
    Prev
    Next
    INDEX
    Explanations

    Victory over

    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
     phénomène
    -0.08
    Tc
    -0.08
    Kind
    -0.08
    Fluid
    -0.08
     fenomen
    -0.07
    .Kind
    -0.07
    .tc
    -0.07
     phenomena
    -0.07
    Facility
    -0.07
    phen
    -0.07
    POSITIVE LOGITS
     erad
    0.15
     борьбы
    0.13
     विजय
    0.13
     combating
    0.13
     مكافحة
    0.12
     chữa
    0.12
     побед
    0.12
     combater
    0.12
     defeating
    0.12
     defeated
    0.12
    Activations Density 0.079%

    No Known Activations