© 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. 78270
    Prev
    Next
    INDEX
    Explanations

    Staircases

    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
     EDIT
    -0.08
     bearbeiten
    -0.08
     postgraduate
    -0.08
    .Edit
    -0.07
     ragaz
    -0.07
     Beckham
    -0.07
     Olímp
    -0.07
     outpatient
    -0.07
    ?”
    -0.07
     genes
    -0.07
    POSITIVE LOGITS
     tallest
    0.11
     taller
    0.10
    高さ
    0.09
     Taller
    0.09
    _height
    0.09
     wächst
    0.09
     staircase
    0.08
     alternating
    0.08
     tall
    0.08
    absor
    0.08
    Activations Density 0.006%

    No Known Activations