© 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. 48195
    Prev
    Next
    INDEX
    Explanations

    say "unreal"

    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
     �
    -0.09
     tightly
    -0.09
     bp
    -0.09
    (bp
    -0.09
     sufficient
    -0.09
     BPA
    -0.09
     TPM
    -0.08
     Protection
    -0.08
     BA
    -0.08
     штраф
    -0.08
    POSITIVE LOGITS
     unreal
    0.33
     Unreal
    0.29
     unrealistic
    0.28
     realist
    0.26
     realism
    0.25
     surreal
    0.25
     真人
    0.23
     realistic
    0.22
     réal
    0.22
     현실
    0.22
    Activations Density 0.008%

    No Known Activations