© 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. 99335
    Prev
    Next
    INDEX
    Explanations

    sound/audio

    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
     stringent
    -0.08
     scrutiny
    -0.08
    chin
    -0.08
    כט
    -0.08
    ڪري
    -0.08
     harde
    -0.08
    base
    -0.08
     juntas
    -0.07
     სამყარ
    -0.07
     тэры
    -0.07
    POSITIVE LOGITS
     animations
    0.10
     sonidos
    0.10
     sonido
    0.09
    Sounds
    0.09
     sounds
    0.09
    Animations
    0.09
    Cooldown
    0.09
    响
    0.09
     વગ
    0.09
     áudio
    0.09
    Activations Density 0.004%

    No Known Activations