© 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. 11-RESID-POST-AA
    11. 46
    Prev
    Next
    INDEX
    Explanations

    no

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     والتح
    -0.09
     EDIT
    -0.08
     todays
    -0.08
     Motiv
    -0.08
     DAY
    -0.08
    party
    -0.08
    лава
    -0.08
    -0.08
    !\
    -0.08
     لتح
    -0.08
    POSITIVE LOGITS
     comment
    0.08
    atives
    0.07
     cam
    0.07
    sts
    0.07
    toe
    0.07
    tor
    0.07
    aiti
    0.07
    nect
    0.07
     yo
    0.07
    206
    0.07
    Activations Density 0.207%
    No Known Activations