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. 30229
    Prev
    Next
    INDEX
    Explanations

    common

    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
    Sav
    -0.08
     Copp
    -0.08
     cam
    -0.08
     Nih
    -0.08
     Lä
    -0.07
    never
    -0.07
    nake
    -0.07
     Savage
    -0.07
     lob
    -0.07
     Dement
    -0.07
    POSITIVE LOGITS
    wealth
    0.13
    -minded
    0.11
    -sama
    0.09
     minded
    0.09
    ality
    0.08
     cle
    0.08
    /shared
    0.08
    oil
    0.08
    /common
    0.08
     wisdom
    0.08
    Activations Density 0.027%

    No Known Activations