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. 67153
    Prev
    Next
    INDEX
    Explanations

    common short words

    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
     gentleman
    -0.08
     tors
    -0.08
     позвоноч
    -0.07
     uncomment
    -0.07
     Dissertation
    -0.07
     ankles
    -0.07
     pallets
    -0.07
     underground
    -0.07
     જમી
    -0.07
     chão
    -0.07
    POSITIVE LOGITS
     cognitive
    0.12
     cognit
    0.11
     Cognitive
    0.10
     perceived
    0.10
     cognition
    0.09
     cues
    0.09
     perceive
    0.09
    strual
    0.09
     perce
    0.09
     beliefs
    0.08
    Activations Density 0.040%

    No Known Activations