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. 76302
    Prev
    Next
    INDEX
    Explanations

    TPM

    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
     sawa
    -0.09
     Premium
    -0.08
     striking
    -0.08
     prescription
    -0.07
    Premium
    -0.07
    -0.07
     zugleich
    -0.07
     premium
    -0.07
     dubb
    -0.07
    ిద్ధ
    -0.07
    POSITIVE LOGITS
     налич
    0.08
    етом
    0.08
    -mediated
    0.08
    .ico
    0.08
    0.08
    Agency
    0.08
     mediation
    0.08
     vorhanden
    0.08
    istory
    0.08
    Tracker
    0.07
    Activations Density 0.000%

    No Known Activations