© 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. 19-RESID-POST-AA
    11. 102678
    Prev
    Next
    INDEX
    Explanations

    {

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.09
     (
    -0.08
     [
    -0.08
     Also
    -0.08
     I'm
    -0.08
     Ident
    -0.08
     https
    -0.08
     AKA
    -0.08
     =
    -0.08
     for
    -0.08
    POSITIVE LOGITS
     }↵↵↵↵↵↵
    0.10
    isoq
    0.10
     };
    0.10
    ît
    0.10
     '}↵
    0.09
    �pp
    0.09
     }↵↵↵
    0.09
     };↵
    0.09
     }
↵
↵
↵
    0.09
    �
    0.09
    Activations Density 0.001%

    No Known Activations