© 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. 96845
    Prev
    Next
    INDEX
    Explanations

    say "rm" word

    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
     fi
    -0.09
    .IN
    -0.08
    Ta
    -0.08
     Ta
    -0.08
     <>
    -0.07
     Mab
    -0.07
     ta
    -0.07
     poo
    -0.07
     �
    -0.07
     الداخلية
    -0.07
    POSITIVE LOGITS
    musik
    0.09
     анд
    0.09
     Partner
    0.08
     Stylish
    0.08
    ,K
    0.08
    ిగా
    0.08
    �
    0.08
    큼
    0.08
    ూమ
    0.08
     vão
    0.08
    Activations Density 0.001%

    No Known Activations