© 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. 11-RESID-POST-AA
    11. 139
    Prev
    Next
    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betray
    -0.07
     foster
    -0.07
    》(
    -0.07
    .callbacks
    -0.07
    》
    -0.07
     initialization
    -0.07
     quello
    -0.07
     callbacks
    -0.07
     المكان
    -0.07
     spett
    -0.07
    POSITIVE LOGITS
     Anzahl
    0.09
     จำนวน
    0.09
    จำนวน
    0.09
     평균
    0.09
    0.08
    数量
    0.08
     montant
    0.08
     moyen
    0.08
     Wahrscheinlichkeit
    0.08
    Radius
    0.08
    Activations Density 0.022%
    No Known Activations