© 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. 95354
    Prev
    Next
    INDEX
    Explanations

    possessive

    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
    ات
    -0.09
    -ac
    -0.08
     Poli
    -0.08
    ને
    -0.08
    货
    -0.08
    此同时
    -0.08
    Slim
    -0.07
    ًا
    -0.07
    Gra
    -0.07
    sein
    -0.07
    POSITIVE LOGITS
     Lund
    0.08
     Ped
    0.08
     സ്വന്തം
    0.08
     Engel
    0.08
     Soc
    0.07
     �
    0.07
    159
    0.07
     paradox
    0.07
     Larry
    0.07
     경우
    0.07
    Activations Density 0.270%

    No Known Activations