© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12959
    Prev
    Next
    INDEX
    Explanations

    user

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     facilitated
    -0.07
     PDA
    -0.07
    _gu
    -0.07
    gd
    -0.07
     enregistr
    -0.07
     Polsce
    -0.07
     IOC
    -0.07
    epad
    -0.07
    wt
    -0.07
    רד
    -0.07
    POSITIVE LOGITS
     lyrical
    0.08
    forth
    0.08
    imonial
    0.08
    num
    0.07
    omi
    0.07
    truck
    0.07
    blick
    0.07
     Zürich
    0.07
    nummer
    0.07
    /song
    0.07
    Activations Density 0.073%

    No Known Activations