© 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. 6135
    Prev
    Next
    INDEX
    Explanations

    period

    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
     sincerity
    -0.08
     filler
    -0.08
    ины
    -0.08
     faveur
    -0.08
    ^[
    -0.07
    不停
    -0.07
    微
    -0.07
    ின
    -0.07
    יע
    -0.07
     Micro
    -0.07
    POSITIVE LOGITS
    cls
    0.09
    čiti
    0.09
     postal
    0.08
    spf
    0.07
     kapsamında
    0.07
    uam
    0.07
     balt
    0.07
    anese
    0.07
    cell
    0.07
    FAA
    0.07
    Activations Density 0.000%

    No Known Activations