© 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. 48114
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     faktiskt
    -0.08
     faktisk
    -0.08
     tatsächlich
    -0.08
     correctly
    -0.07
    ויב
    -0.07
     confirmed
    -0.07
     effectivement
    -0.07
     실제
    -0.07
     selbstverständlich
    -0.07
    utanga
    -0.07
    POSITIVE LOGITS
     difficult
    0.41
     difficiles
    0.38
     difícil
    0.37
     moeilijk
    0.37
     сложно
    0.37
     difíciles
    0.37
     difíceis
    0.37
     Hard
    0.36
     difficile
    0.36
     complicado
    0.35
    Activations Density 0.302%

    No Known Activations