© 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. 2620
    Prev
    Next
    INDEX
    Explanations

    to

    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
     wag
    -0.08
     lob
    -0.08
     берег
    -0.08
     NAS
    -0.08
     cav
    -0.07
     engr
    -0.07
     shoulder
    -0.07
    Bug
    -0.07
    68
    -0.07
     pata
    -0.07
    POSITIVE LOGITS
     cardinal
    0.10
     Carroll
    0.08
     δυ
    0.08
     Sexy
    0.08
     определения
    0.08
     santa
    0.07
     Cardinal
    0.07
     Christian
    0.07
     значения
    0.07
     isc
    0.07
    Activations Density 0.011%

    No Known Activations