© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 51986
    Prev
    Next
    INDEX
    Explanations

    terms

    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
    Sequences
    -0.13
    _sequences
    -0.11
    Queues
    -0.11
     sequences
    -0.11
    Paths
    -0.10
     Chains
    -0.10
     Paths
    -0.09
     circuits
    -0.09
    Chains
    -0.09
    (paths
    -0.09
    POSITIVE LOGITS
     terms
    0.46
    _terms
    0.39
     términos
    0.39
    terms
    0.38
     Terms
    0.38
     termes
    0.38
    Terms
    0.37
     termos
    0.34
     term
    0.30
     TERMS
    0.30
    Activations Density 0.141%

    No Known Activations