Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 47031
    Prev
    Next
    INDEX
    Explanations

    first person objective games

    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
    .Gravity
    -0.09
    .Serv
    -0.09
    _eq
    -0.08
    ково
    -0.08
    .mount
    -0.08
    ож
    -0.08
    улу
    -0.08
    ulan
    -0.07
    èl
    -0.07
    ули
    -0.07
    POSITIVE LOGITS
     നേട
    0.08
     manners
    0.08
     años
    0.08
     alcanza
    0.08
     sanat
    0.07
     lõpet
    0.07
     est
    0.07
     gane
    0.07
     nurse
    0.07
     pengar
    0.07
    Activations Density 0.005%

    No Known Activations