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. 113862
    Prev
    Next
    INDEX
    Explanations

    1

    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
    apost
    -0.09
    astaan
    -0.08
    Bah
    -0.08
    ੰਜ
    -0.08
    ittings
    -0.08
    Forms
    -0.08
    BSD
    -0.08
    ayanan
    -0.08
    anj
    -0.07
    unteer
    -0.07
    POSITIVE LOGITS
     тщ
    0.08
     entsprechenden
    0.07
     установить
    0.07
     Stell
    0.07
     внимательно
    0.07
    sss
    0.07
     
    0.07
     entsprechende
    0.07
     nemo
    0.07
     Parties
    0.07
    Activations Density 0.041%

    No Known Activations