© 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. 23-RESID-POST-AA
    11. 6208
    Prev
    Next
    INDEX
    Explanations

    R

    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
    Über
    -0.09
     Über
    -0.09
     Gewer
    -0.08
    ł
    -0.08
    ls
    -0.08
    aan
    -0.07
    �
    -0.07
    ╗
    -0.07
    _OVER
    -0.07
    Nós
    -0.07
    POSITIVE LOGITS
    CEP
    0.13
     cercana
    0.08
     FFT
    0.08
    _mp
    0.07
     الخليج
    0.07
     Quartet
    0.07
     אמ
    0.07
    IMER
    0.07
     treff
    0.07
    _MP
    0.07
    Activations Density 0.000%

    No Known Activations