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. 3-RESID-POST-AA
    6. 2458
    Prev
    Next
    INDEX
    Explanations

    GDBus 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_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    甜
    -0.09
     eeg
    -0.07
     roulette
    -0.07
     Genes
    -0.07
     sweet
    -0.07
    -self
    -0.07
     juggling
    -0.07
     completo
    -0.07
     deserts
    -0.07
    _STA
    -0.07
    POSITIVE LOGITS
     gchar
    0.08
     Petsc
    0.08
    OBJECT
    0.08
     Henri
    0.08
    strncmp
    0.08
     gboolean
    0.08
    keeper
    0.08
     spur
    0.08
     Blanc
    0.08
     ctxt
    0.08
    Activations Density 0.025%

    No Known Activations