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. 76720
    Prev
    Next
    INDEX
    Explanations

    Finding lost items

    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
     fas
    -0.09
     censorship
    -0.07
     feeding
    -0.07
     judge
    -0.07
     Rank
    -0.07
    .cols
    -0.07
     alimentar
    -0.07
     honorary
    -0.07
     wata
    -0.07
     proclamation
    -0.07
    POSITIVE LOGITS
     misplaced
    0.15
     elusive
    0.12
     verloren
    0.12
     चोरी
    0.11
     whereabouts
    0.11
     perdido
    0.11
     perdida
    0.10
     നഷ്ട
    0.10
    _missing
    0.10
     missing
    0.10
    Activations Density 0.075%

    No Known Activations