© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 47968
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     conjuntos
    -0.09
    canf
    -0.08
     devastation
    -0.08
    .construct
    -0.08
     costo
    -0.08
    _stdio
    -0.07
     moist
    -0.07
    _ascii
    -0.07
    adern
    -0.07
    ayment
    -0.07
    POSITIVE LOGITS
    123
    0.11
    899
    0.09
    330
    0.08
    358
    0.08
    743
    0.08
    898
    0.08
    älla
    0.08
    472
    0.08
    242
    0.08
    :on
    0.07
    Activations Density 0.002%

    No Known Activations