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. 8946
    Prev
    Next
    INDEX
    Explanations

    istant

    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
     можлив
    -0.07
     મહ
    -0.07
     pyl
    -0.07
     jede
    -0.07
     ді
    -0.07
     či
    -0.07
     stær
    -0.07
     expiry
    -0.07
     Angel
    -0.07
     livelihoods
    -0.07
    POSITIVE LOGITS
     (=
    0.09
     therefore
    0.09
     hence
    0.08
     hoogte
    0.08
    UC
    0.08
     associ
    0.08
     FHA
    0.08
    ention
    0.08
    ocidad
    0.08
    Сп
    0.07
    Activations Density 0.008%

    No Known Activations