© 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. 5997
    Prev
    Next
    INDEX
    Explanations

    Numerical sequence

    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
     إمكانية
    -0.10
     придется
    -0.10
     måste
    -0.09
    必须
    -0.09
    不会
    -0.09
     સહિત
    -0.09
    .must
    -0.08
     любые
    -0.08
     devront
    -0.08
     любых
    -0.08
    POSITIVE LOGITS
     nth
    0.16
     successive
    0.16
     starting
    0.15
     increasing
    0.15
     sequence
    0.15
     Sequence
    0.15
    nth
    0.15
     seems
    0.15
     pattern
    0.15
     Increasing
    0.15
    Activations Density 0.182%

    No Known Activations