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. 29885
    Prev
    Next
    INDEX
    Explanations

    cash

    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
    (Note
    -0.08
     pu
    -0.08
     Lees
    -0.08
     Ia
    -0.08
     peuples
    -0.07
     Pok
    -0.07
     Rolle
    -0.07
     incar
    -0.07
    .github
    -0.07
     HAS
    -0.07
    POSITIVE LOGITS
    worthiness
    0.09
    mere
    0.08
     donations
    0.08
     де
    0.08
    状
    0.08
    strap
    0.08
    рат
    0.08
    worthy
    0.08
    สด
    0.08
     Arg
    0.07
    Activations Density 0.009%

    No Known Activations