© 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. 47979
    Prev
    Next
    INDEX
    Explanations

    think

    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
     Which
    -0.12
     Apparently
    -0.12
     How
    -0.12
     Seems
    -0.11
    How
    -0.10
     seem
    -0.10
     Used
    -0.10
     Various
    -0.09
     hvilke
    -0.09
     Feel
    -0.09
    POSITIVE LOGITS
     it's
    0.29
     that's
    0.27
     we
    0.23
     there's
    0.22
     they'd
    0.20
     they
    0.20
     we'll
    0.19
    that's
    0.19
     this
    0.19
     we'd
    0.19
    Activations Density 0.040%

    No Known Activations