© 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. 48706
    Prev
    Next
    INDEX
    Explanations

    denominator

    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
     Junio
    -0.08
    níomh
    -0.07
    jál
    -0.07
    .spark
    -0.07
     spies
    -0.07
     suor
    -0.07
     ★
    -0.07
    
    -0.07
     чара
    -0.07
     বিশ্বের
    -0.07
    POSITIVE LOGITS
     denominator
    0.68
     denom
    0.59
     denomin
    0.59
    Den
    0.54
     Den
    0.54
    den
    0.52
    _den
    0.51
    -den
    0.47
    .den
    0.46
    _DEN
    0.45
    Activations Density 0.379%

    No Known Activations