© 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. 48142
    Prev
    Next
    INDEX
    Explanations

    neurological conditions

    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
    'économie
    -0.09
    ódigo
    -0.08
     economía
    -0.08
    ’économie
    -0.08
     economy
    -0.08
    paras
    -0.08
    -0.08
    inas
    -0.08
     Economía
    -0.08
     paral
    -0.08
    POSITIVE LOGITS
     yuq
    0.08
     কঠ
    0.07
     自
    0.07
     essential
    0.07
     articulation
    0.07
     Free
    0.07
     rédaction
    0.07
     careg
    0.07
    awk
    0.07
    _FREE
    0.07
    Activations Density 0.004%
    No Known Activations