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. 65151
    Prev
    Next
    INDEX
    Explanations

    Karma Yoga

    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
     validity
    -0.09
     VALID
    -0.09
     Invalid
    -0.09
    ీట్
    -0.09
    valid
    -0.09
     graet
    -0.08
     invalid
    -0.08
     Valid
    -0.08
    ांग्रेस
    -0.08
     validation
    -0.08
    POSITIVE LOGITS
    心
    0.10
    淡
    0.10
     fluctuate
    0.10
     émotion
    0.09
     emotionally
    0.09
     emocional
    0.09
     impartial
    0.09
    lıkl
    0.09
    忧
    0.09
     शांत
    0.09
    Activations Density 0.020%

    No Known Activations