Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44164
    Prev
    Next
    INDEX
    Explanations

    audio, music

    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
     cred
    -0.08
     terrorism
    -0.08
    Reusable
    -0.08
     consommation
    -0.08
     peacefully
    -0.08
     peaceful
    -0.08
     Christ
    -0.07
     violence
    -0.07
    徒
    -0.07
    Crime
    -0.07
    POSITIVE LOGITS
     amplifier
    0.12
    滤
    0.11
     frequencies
    0.10
    -filter
    0.10
     bandwidth
    0.10
     notch
    0.10
     headphone
    0.10
    filters
    0.09
     octave
    0.09
     tuning
    0.09
    Activations Density 0.020%

    No Known Activations