© 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. 3-RESID-POST-AA
    11. 12839
    Prev
    Next
    INDEX
    Explanations

    and ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    echo
    -0.08
     accountable
    -0.08
     Eric
    -0.08
    tir
    -0.07
     dig
    -0.07
    му
    -0.07
    weighted
    -0.07
    loan
    -0.07
    feeds
    -0.07
     excel
    -0.07
    POSITIVE LOGITS
     possibilité
    0.09
    _SN
    0.08
     MMM
    0.08
     ज
    0.07
     fragile
    0.07
    ിക്കുന്നത്
    0.07
    snippet
    0.07
    _strings
    0.07
    .xxx
    0.07
    Sect
    0.07
    Activations Density 0.034%

    No Known Activations