© 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. 6179
    Prev
    Next
    INDEX
    Explanations

    degener

    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
    иях
    -0.09
    umäng
    -0.09
    ielsweise
    -0.09
     万国
    -0.08
    ortut
    -0.08
    яў
    -0.08
    иғ
    -0.08
    、中
    -0.08
    უალ
    -0.08
    ៌
    -0.08
    POSITIVE LOGITS
    acy
    0.25
    acies
    0.22
    escence
    0.20
    enerate
    0.19
    ative
    0.16
    ACY
    0.16
    enerated
    0.14
    ately
    0.14
    ener
    0.12
    ates
    0.12
    Activations Density 0.002%

    No Known Activations