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. 23617
    Prev
    Next
    INDEX
    Explanations

    medical symptoms

    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
     eins
    -0.08
    heses
    -0.08
     chcia
    -0.08
     coluna
    -0.08
     progressively
    -0.08
     cabelo
    -0.08
     static
    -0.07
     हवा
    -0.07
     deterministic
    -0.07
     column
    -0.07
    POSITIVE LOGITS
    Silent
    0.11
     atyp
    0.11
     Silent
    0.11
     disguised
    0.11
     sermons
    0.10
     disguise
    0.09
     disguis
    0.09
     unusual
    0.08
     Silence
    0.08
     Unexpected
    0.08
    Activations Density 0.011%

    No Known Activations