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. 101641
    Prev
    Next
    INDEX
    Explanations

    Numerical calculations

    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
     candidatos
    -0.08
     Mujeres
    -0.08
    #region
    -0.08
    -inst
    -0.08
     candidats
    -0.07
     paragraphs
    -0.07
    wlet
    -0.07
     Madison
    -0.07
    ahit
    -0.07
    Coment
    -0.07
    POSITIVE LOGITS
     slightly
    0.08
     rebel
    0.08
     ng
    0.08
     Modify
    0.08
     Ng
    0.07
     Barney
    0.07
     nuances
    0.07
    账
    0.07
     MODIFY
    0.07
    -but
    0.07
    Activations Density 0.018%

    No Known Activations