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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120426
    Prev
    Next
    INDEX
    Explanations

    plants

    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
    Maz
    -0.08
     mals
    -0.08
    noma
    -0.08
     Expedition
    -0.08
    abol
    -0.07
     pressures
    -0.07
     Abenteuer
    -0.07
     Alias
    -0.07
     cruise
    -0.07
    ائش
    -0.07
    POSITIVE LOGITS
    @class
    0.08
     ike
    0.07
     peas
    0.07
    」は
    0.07
     तरफ
    0.07
     Think
    0.07
    担
    0.07
     atoms
    0.07
    自身
    0.07
    =edge
    0.07
    Activations Density 0.004%

    No Known Activations