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. 65636
    Prev
    Next
    INDEX
    Explanations

    suffixes ending in "y"

    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
     encuent
    -0.09
    Shar
    -0.09
     trovi
    -0.09
     Mol
    -0.08
     allt
    -0.08
    Arch
    -0.08
    מוד
    -0.08
     Shar
    -0.08
    Mol
    -0.08
     bara
    -0.08
    POSITIVE LOGITS
     whims
    0.10
     Arbitr
    0.09
    .choice
    0.09
     arbitrary
    0.08
     choices
    0.08
     வித
    0.08
     decree
    0.08
     nonce
    0.08
    ило
    0.07
     norms
    0.07
    Activations Density 0.006%

    No Known Activations