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. 29877
    Prev
    Next
    INDEX
    Explanations

    developed countries

    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
     besar
    -0.09
     yang
    -0.08
     enlarg
    -0.07
     который
    -0.07
     hasard
    -0.07
     punto
    -0.07
     etc
    -0.07
     Cu
    -0.07
     administrar
    -0.07
     scalable
    -0.07
    POSITIVE LOGITS
     modernos
    0.09
     enweghị
    0.09
     urbanos
    0.09
    -European
    0.08
     affluent
    0.08
     históricos
    0.08
     technolog
    0.08
     anaghị
    0.08
     suburban
    0.08
     ụfọdụ
    0.08
    Activations Density 0.057%

    No Known Activations