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. 12700
    Prev
    Next
    INDEX
    Explanations

    Database code

    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
     machining
    -0.08
     uitzicht
    -0.08
    508
    -0.08
     sensores
    -0.08
     sightings
    -0.07
     bothering
    -0.07
    IGHTS
    -0.07
     descre
    -0.07
     naš
    -0.07
    >>↵↵
    -0.07
    POSITIVE LOGITS
     याद
    0.08
    itest
    0.08
    jord
    0.08
    (password
    0.08
     onth
    0.08
     suggest
    0.08
     random
    0.07
     Oficina
    0.07
     welcoming
    0.07
     Соз
    0.07
    Activations Density 0.002%

    No Known Activations