© 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. 96889
    Prev
    Next
    INDEX
    Explanations

    say "soft"

    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
     skilled
    -0.17
     Skilled
    -0.15
     skills
    -0.12
    Skill
    -0.12
    _skill
    -0.12
    技能
    -0.11
    -skilled
    -0.11
     skill
    -0.11
     Skill
    -0.11
     Skills
    -0.10
    POSITIVE LOGITS
     soft
    0.29
    soft
    0.26
     Soft
    0.26
    Soft
    0.25
    软
    0.25
    _soft
    0.24
    .soft
    0.22
     softer
    0.22
     zachte
    0.21
    -soft
    0.21
    Activations Density 0.024%

    No Known Activations