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. 43672
    Prev
    Next
    INDEX
    Explanations

    titles

    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
    Zones
    -0.08
    zones
    -0.08
     BUT
    -0.08
    र्स
    -0.08
    ونه
    -0.08
    [file
    -0.07
    Ah
    -0.07
    Bu
    -0.07
    .One
    -0.07
    vari
    -0.07
    POSITIVE LOGITS
     vertrouwen
    0.09
     Salvador
    0.08
     V
    0.08
     Adri
    0.08
     kraft
    0.08
    ike
    0.07
     Kj
    0.07
     dbg
    0.07
     trygg
    0.07
    �
    0.07
    Activations Density 0.050%

    No Known Activations