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. 43645
    Prev
    Next
    INDEX
    Explanations

    crystallized intelligence

    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
     literals
    -0.09
    logan
    -0.08
     existem
    -0.08
     ஐ
    -0.08
     Offshore
    -0.08
    .Middle
    -0.07
    naf
    -0.07
     tweaks
    -0.07
     Headlines
    -0.07
    YSTEM
    -0.07
    POSITIVE LOGITS
     sealed
    0.08
     wett
    0.08
    ума
    0.08
     vlak
    0.08
     major
    0.08
     jeung
    0.07
     wet
    0.07
     kurzfrist
    0.07
     communion
    0.07
    crate
    0.07
    Activations Density 0.002%

    No Known Activations