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. 29826
    Prev
    Next
    INDEX
    Explanations

    electricity, circuits

    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
     auteur
    -0.08
     perguntar
    -0.08
     assunto
    -0.08
     обсуж
    -0.08
     genetics
    -0.08
     വിഷയ
    -0.08
     beziehen
    -0.08
     sujeito
    -0.08
     fragen
    -0.08
    讨论
    -0.08
    POSITIVE LOGITS
     cushioning
    0.12
     absorbs
    0.11
     stopper
    0.10
     mitigation
    0.10
    挡
    0.10
     रोक
    0.10
     resisting
    0.10
     deterr
    0.10
     absorb
    0.10
     absorber
    0.09
    Activations Density 0.016%

    No Known Activations