© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78898
    Prev
    Next
    INDEX
    Explanations

    elegant

    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
    լին
    -0.11
    ucking
    -0.09
    նայած
    -0.09
     mett
    -0.09
     voorzitter
    -0.09
    կա
    -0.09
     hökü
    -0.08
    յանն
    -0.08
    აკეთ
    -0.08
    })
    ↵
    -0.08
    POSITIVE LOGITS
     атмос
    0.09
     atmosphere
    0.08
    Atmos
    0.08
     atmos
    0.08
    _entry
    0.08
     Atmos
    0.08
    amage
    0.07
     connections
    0.07
    -style
    0.07
     \(
    0.07
    Activations Density 0.020%

    No Known Activations