Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78646
    Prev
    Next
    INDEX
    Explanations

    Stake

    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
    到底
    -0.08
    מה
    -0.08
     paš
    -0.08
    Endpoints
    -0.08
    Leadership
    -0.08
     schafft
    -0.08
    Vai
    -0.07
     atribu
    -0.07
    Via
    -0.07
    Vest
    -0.07
    POSITIVE LOGITS
     Bü
    0.09
     magazine
    0.08
     SINGLE
    0.08
     magazines
    0.08
     हवा
    0.08
     diluted
    0.07
     alloys
    0.07
     Mailing
    0.07
     sparse
    0.07
     SPR
    0.07
    Activations Density 0.001%

    No Known Activations