© 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. 23-RESID-POST-AA
    6. 6003
    Prev
    Next
    INDEX
    Explanations

    Code and logic

    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
    similar
    -0.12
     similar
    -0.12
     ähnlich
    -0.12
    类似
    -0.11
     Similar
    -0.11
     Specific
    -0.10
     similaires
    -0.10
     specific
    -0.10
     similares
    -0.10
    specific
    -0.10
    POSITIVE LOGITS
     albeit
    0.14
     dezelfde
    0.11
     except
    0.11
     กัน
    0.10
     تقريب
    0.10
     gebleven
    0.10
    except
    0.10
     applies
    0.10
     structure
    0.09
    Except
    0.09
    Activations Density 0.113%

    No Known Activations