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. 53198
    Prev
    Next
    INDEX
    Explanations

    truthfulness

    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
    comfort
    -0.10
     Komfort
    -0.09
     ersetzt
    -0.09
     komfort
    -0.09
    zere
    -0.09
     reakc
    -0.09
     Escol
    -0.08
    zg
    -0.08
     Ribe
    -0.08
     Comfort
    -0.08
    POSITIVE LOGITS
    〇
    0.08
     liar
    0.08
     propos
    0.08
     অস্ত
    0.08
     shall
    0.08
     imminent
    0.08
     premise
    0.07
     premises
    0.07
    972
    0.07
     blah
    0.07
    Activations Density 0.015%

    No Known Activations