© 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. 47990
    Prev
    Next
    INDEX
    Explanations

    Peng

    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
    েলার
    -0.09
    ിപ്പ്
    -0.08
    িয়
    -0.08
     jiru
    -0.08
     scola
    -0.08
    äre
    -0.08
    েলা
    -0.07
    ениями
    -0.07
     ас
    -0.07
    Autocomplete
    -0.07
    POSITIVE LOGITS
    ikt
    0.09
    sst
    0.09
     Kathy
    0.08
     Donna
    0.08
    urst
    0.08
     साफ
    0.08
     kt
    0.08
    ktime
    0.08
     RH
    0.08
    ktan
    0.08
    Activations Density 0.000%

    No Known Activations