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. 41985
    Prev
    Next
    INDEX
    Explanations

    cover

    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
     work
    -0.09
    annut
    -0.08
     technology
    -0.08
     leverage
    -0.07
    unga
    -0.07
     harmful
    -0.07
    グ
    -0.07
     Aktion
    -0.07
     right
    -0.07
     algorithm
    -0.07
    POSITIVE LOGITS
     sebagian
    0.09
     défaut
    0.09
     cercle
    0.09
     defecto
    0.08
    -picker
    0.08
     davant
    0.08
     большин
    0.08
     Tears
    0.08
     Availability
    0.08
     odl
    0.08
    Activations Density 0.000%

    No Known Activations