© 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. 11-RESID-POST-AA
    11. 24709
    Prev
    Next
    INDEX
    Explanations

    was

    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
    ਿਤ
    -0.09
    ਤਰ
    -0.08
    ].↵↵
    -0.08
     electricidad
    -0.07
    ]:↵↵
    -0.07
    زم
    -0.07
    Uses
    -0.07
    schema
    -0.07
    ਾਇਆ
    -0.07
    useks
    -0.07
    POSITIVE LOGITS
     weaknesses
    0.11
     कमजोर
    0.10
     कमज
    0.09
    _HP
    0.09
     weakness
    0.09
     দুর
    0.09
     destabil
    0.08
     ennem
    0.08
    敵
    0.08
    敌
    0.08
    Activations Density 0.101%

    No Known Activations