© 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. 102904
    Prev
    Next
    INDEX
    Explanations

    old

    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
     procedure
    -0.10
     topology
    -0.08
     procédure
    -0.08
    Topology
    -0.08
     procédures
    -0.08
     അത്
    -0.08
    Landing
    -0.07
     bestaande
    -0.07
     കൂടുതൽ
    -0.07
     methodology
    -0.07
    POSITIVE LOGITS
     are
    0.10
     são
    0.10
     jsou
    0.09
     являются
    0.09
     ছিলেন
    0.09
     ہیں
    0.08
    ležit
    0.08
    irty
    0.08
    ?”.
    0.08
     ampak
    0.08
    Activations Density 0.006%

    No Known Activations