© 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. 23-RESID-POST-AA
    11. 48540
    Prev
    Next
    INDEX
    Explanations

    Leaning ladders/rods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     territories
    -0.10
     territori
    -0.10
     recurring
    -0.09
     Territories
    -0.09
     territ
    -0.09
     เขต
    -0.09
     territorio
    -0.09
     Territory
    -0.09
     กรุงเทพ
    -0.08
     حوزه
    -0.08
    POSITIVE LOGITS
     hinged
    0.20
     pivot
    0.19
     hinge
    0.19
     pulley
    0.18
    杆
    0.18
     rod
    0.18
    Pivot
    0.18
     балки
    0.17
    pivot
    0.17
     torque
    0.16
    Activations Density 0.047%

    No Known Activations