© 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. 48522
    Prev
    Next
    INDEX
    Explanations

    Ü

    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
    っぱ
    -0.08
     gg
    -0.07
     Compute
    -0.07
    imeo
    -0.07
    ondo
    -0.07
     padx
    -0.07
     hiding
    -0.07
     not
    -0.07
     environmentally
    -0.07
    i
    -0.07
    POSITIVE LOGITS
    cretsiz
    0.10
    �영
    0.09
    契
    0.09
     vacature
    0.09
    閱
    0.09
    recipe
    0.08
    CRET
    0.08
     ори
    0.08
     müq
    0.08
    versammlung
    0.08
    Activations Density 0.000%

    No Known Activations