© 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. 30965
    Prev
    Next
    INDEX
    Explanations

    Flask

    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
     utilisées
    -0.08
     individuelles
    -0.08
    gebied
    -0.08
    represented
    -0.08
    æ
    -0.08
     marginal
    -0.08
    atiem
    -0.07
    ා
    -0.07
    �
    -0.07
    ానం
    -0.07
    POSITIVE LOGITS
     UID
    0.08
    UNIC
    0.08
     Saj
    0.08
     SK
    0.08
     Cinnamon
    0.08
    DISC
    0.08
     diver
    0.08
    Jo
    0.08
    Ja
    0.07
     vibe
    0.07
    Activations Density 0.001%

    No Known Activations