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. 119901
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     cylindrical
    -0.09
     цилинд
    -0.08
    الإ
    -0.08
    층
    -0.08
    imp
    -0.08
    azon
    -0.08
     Ալ
    -0.08
    νομα
    -0.08
    prenom
    -0.08
     kjem
    -0.08
    POSITIVE LOGITS
     Fig
    0.08
     Time
    0.08
     colori
    0.07
     Motion
    0.07
     forg
    0.07
     Dynamics
    0.07
    tis
    0.07
    116
    0.07
     Degrees
    0.07
     au
    0.07
    Activations Density 0.001%

    No Known Activations