© 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. 3-RESID-POST-AA
    11. 2541
    Prev
    Next
    INDEX
    Explanations

    Inc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ek
    -0.08
     curt
    -0.08
    Ek
    -0.07
     equil
    -0.07
    ပါ
    -0.07
     turístico
    -0.07
     Pri
    -0.07
     mercury
    -0.07
     Anschluss
    -0.07
     salut
    -0.07
    POSITIVE LOGITS
     iff
    0.08
    �
    0.08
    acf
    0.07
    ffic
    0.07
     Pocket
    0.07
     �
    0.07
     fatty
    0.07
    IAL
    0.07
     Cola
    0.07
    yang
    0.07
    Activations Density 0.005%

    No Known Activations