© 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. 96684
    Prev
    Next
    INDEX
    Explanations

    Native

    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
    ned
    -0.08
    ded
    -0.08
    ovao
    -0.08
    ainty
    -0.08
    thest
    -0.08
    ulot
    -0.08
     original
    -0.08
     those
    -0.07
    nec
    -0.07
    nea
    -0.07
    POSITIVE LOGITS
     americans
    0.16
     Hawaiian
    0.14
    -born
    0.14
     speaker
    0.13
     speakers
    0.13
     American
    0.13
     Hawai
    0.13
     Americans
    0.12
     अमेरिक
    0.12
    -speaking
    0.12
    Activations Density 0.006%

    No Known Activations