© 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. 96694
    Prev
    Next
    INDEX
    Explanations

    seek

    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
    Här
    -0.09
    (nameof
    -0.09
    atika
    -0.09
     mas
    -0.08
    రూ
    -0.08
    -masing
    -0.08
     ru
    -0.08
    -da
    -0.08
     punts
    -0.08
    're
    -0.08
    POSITIVE LOGITS
     seek
    0.14
    seek
    0.12
    Seek
    0.12
     seeks
    0.12
     Seek
    0.11
     Se
    0.11
     cont
    0.10
    _seek
    0.10
     mis
    0.09
     I
    0.09
    Activations Density 0.007%

    No Known Activations