© 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. 19-RESID-POST-AA
    11. 102952
    Prev
    Next
    INDEX
    Explanations

    phase transition

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minted
    -0.10
     standings
    -0.10
     outfits
    -0.10
     beneficiaries
    -0.09
     leaderboard
    -0.09
     HOLDERS
    -0.09
     jersey
    -0.09
     paycheck
    -0.09
     query
    -0.09
     beneficiary
    -0.09
    POSITIVE LOGITS
     onset
    0.19
     threshold
    0.17
     hyster
    0.15
    threshold
    0.15
    Threshold
    0.14
     thresholds
    0.14
    _threshold
    0.14
     Threshold
    0.14
     melting
    0.13
     transition
    0.13
    Activations Density 0.020%

    No Known Activations